SOURCE-LINKED INTELLIGENCE

RoMa-$Ω$: What Feed-Forward 3D Models Know About Image Matching

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Learned image matching has experienced significant progress in recent years, culminating in robust and accurate matchers such as RoMa, whose robustness is often attributed to its use of frozen DINO features. In a parallel development, feed-forward reconstruction models, such as VGGT, have been trained on ever-growing datasets to accurately regress dense 3D point maps and camera poses. The distinction between matchers and feed-forward reconstruction models has become increasingly blurred with the introduction of matching losses in models such as MASt3R and VGGT-$Ω$. This raises a natural questi

Read original source ↗ Open in workspace

recordType

paper

region

Global